INDEX

Explanations

verbs related to communication or actions

oai_token-act-pair · gpt-3.5-turbo

action verbs related to announcements, participation, and investigations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quart

-0.76

è¦ļéĨĴ

-0.71

assing

-0.65

Pic

-0.65

 supposed

-0.65

pmwiki

-0.65

cas

-0.64

>>\

-0.62

Cas

-0.61

she

-0.59

POSITIVE LOGITS

 tomorrow

0.81

enance

0.79

ãĥį

0.76

ELY

0.72

vt

0.70

igate

0.69

ãĤ¿

0.68

ãĥ¼ãĥ

0.66

ezvous

0.66

 anytime

0.66

Activations Density 0.431%

verbs related to communication or actions

action verbs related to announcements, participation, and investigations

No Comments

No Known Activations